atomicarchitects/equiformer_v2

[ICLR 2024] EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations

44
/ 100
Emerging

This project offers a sophisticated AI model for materials scientists and computational chemists. It takes 3D atomic structures as input and accurately predicts their energy and forces, which are crucial for understanding material behavior and chemical reactions. This tool is designed for researchers and engineers working on novel materials discovery and optimization.

328 stars. No commits in the last 6 months.

Use this if you need highly accurate predictions of atomic forces and energies for 3D molecular or material structures, particularly for catalyst design and simulations.

Not ideal if you are a Python developer seeking a general-purpose library for building arbitrary equivariant models, or if you don't work with atomistic systems.

materials-science computational-chemistry catalysis molecular-dynamics novel-materials-discovery
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

328

Forks

45

Language

Python

License

MIT

Last pushed

Feb 11, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/atomicarchitects/equiformer_v2"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.